Skip to main content
Glama
TMHSDigital

Steam MCP Server

by TMHSDigital
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

steam_uploadLeaderboardScore

Upload or update a player's score on a Steam leaderboard using the partner API. Requires a publisher key and IP allowlist; dry-run previews the request before confirmation.

Instructions

MUTATES LIVE LEADERBOARD ENTRY. Default dry_run=true; requires confirm=true to send. Upload a score to a Steam leaderboard via the partner API. Requires a publisher API key with server IP allowlisted in Steamworks partner settings.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
appidYesSteam application ID
scoreYesScore to upload (interpretation depends on leaderboard sort method)
confirmNoRequired true when dry_run is false. Refuses otherwise.
dry_runNoIf true (default), return the planned request without contacting Steam
steamidYes64-bit Steam ID of the player
scoremethodNoKeepBest only updates if better than existing; ForceUpdate always overwrites (default: KeepBest)
leaderboardidYesNumeric leaderboard ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.9.0
    • addedInput schema / properties / confirm
      Added value: +{
+  "description": "Required true when dry_run is false. Refuses otherwise.",
+  "type": "boolean"
+}
    • addedInput schema / properties / dry_run
      Added value: +{
+  "description": "If true (default), return the planned request without contacting Steam",
+  "type": "boolean"
+}
  2. First observedv0.7.0

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full safety burden. It explicitly warns about live mutation, discloses the dry-run default and confirm requirement to prevent accidental writes, and reveals the API key/IP allowlist prerequisite. This is strong behavioral disclosure for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and every sentence carries useful information. It loses a point for slight redundancy between 'MUTATES LIVE LEADERBOARD ENTRY' and 'Upload a score...', and for placing the action sentence after the dry-run/confirm sentence instead of leading with it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description plus the fully documented schema cover the core behavior, safety flow, and auth prerequisites. Missing details are minor but noticeable: there is no description of the live response/error shape and no explicit guidance distinguishing this from read or listing leaderboard tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the parameter descriptions already document defaults, enums, and constraints such as confirm being required when dry_run is false. The prose adds emphasis on the dry_run/confirm relationship but does not materially add meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: 'Upload a score to a Steam leaderboard' and explicitly identifies this as 'MUTATES LIVE LEADERBOARD ENTRY.' This clearly distinguishes it from read-only siblings like steam_getLeaderboardEntries and steam_getLeaderboardsForGame.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear operational context: dry_run defaults to true, confirm=true is required to actually send, and a publisher API key with an allowlisted IP is required. It does not explicitly name sibling alternatives or state when not to use the tool, which keeps it from a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools